arxivcs.CV2026-06-26
Understanding How MLLMs Describe Artworks Using Token Activation Maps
Nicola Fanelli, Pasquale De Marinis, Raffaele Scaringi, Eva Cetinic, Gennaro Vessio, Giovanna Castellano
Multimodal Large Language Models (MLLMs) describe artworks with remarkable fluency, yet the visual reasoning behind their outputs remains opaque. When an MLLM names a style, identifies a subject, or recognizes an iconographic symbol, does it ground each claim in the relevant regi…